AI: Machines Can Learn Like Humans, Study Finds

The researchers concluded that the BPL approach “can perform one-shot learning in classification tasks at human-level accuracy and fool most judges in visual Turing tests of its more creative abilities”. During a demonstration on their work, the scientists said they’ve not only built a machine-learning program, “but what the application learns – its notions – are additionally programs”. The software was developed by Brendan Lake, a researcher at New York University, together with Ruslan Salakhutdinov, an assistant professor of computer science at the University of Toronto, and Joshua Tenenbaum, a professor in the Department of Brain and Cognitive Sciences at MIT. In the recent work, the researchers have tried to reduce the learning process and make it more similar to the way grasp and apply the new concepts. “But if…

Link to Full Article: AI: Machines Can Learn Like Humans, Study Finds

Pin It on Pinterest

Share This